nbeerbower/mistral-nemo-kartoffel-PRUNE

Partial fine-tune vs nbeerbower/mistral-nemo-kartoffel-12B. Partial change: 16% of the weights changed (attention, mlp, norms), in 6 of 32 layers.

Tensors changed: Embeddings 0/1, Norms 12/65, MLP 18/96, Attention 24/128, lm_head 0/1

1 derivatives checked

On the Hub · Downloads on Model Pulse